OpenAI: GPT-4o Audio

GPT

Multimodal

Paid

The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences. Audio outputs are currently not supported. Audio tokens are priced at $40 per million input and $80 per million output audio tokens.

Parameters

~1.8T

Context Window

128,000

tokens

Input Price

$2.5

per 1M tokens

Output Price

$10

per 1M tokens

Capabilities

Model capabilities and supported modalities

Performance

Reasoning

Excellent reasoning capabilities with strong logical analysis

Math

Strong mathematical capabilities, handles complex calculations well

Coding

Strong coding abilities across multiple programming languages

Knowledge

Extensive knowledge base with broad coverage of topics

Modalities

Input Modalities

audio,text

Output Modalities

text,audio

LLM Price Calculator

Calculate the cost of using this model

Input Tokens (0.00000250/token)$0.003750

Output Tokens (0.00001000/token)$0.030000

Common Scenarios:

Input Cost:$0.003750

Output Cost:$0.030000

Total Cost:$0.033750

Estimated usage: 4,500 tokens

Monthly Cost Estimator

Based on different usage levels

Light Usage

$0.1250

~10 requests

Moderate Usage

$1.2500

~100 requests

Heavy Usage

$12.5000

~1000 requests

Enterprise

$125.0000

~10,000 requests

Note: Estimates based on current token count settings per request.

Last Updated: 2026/02/15